cli-anything-hermes — Hermes skill for Claude Code: wrap GUI as CLI
cli-anything-hermes — a Hermes agent skill that builds CLI wrappers over graphical applications and repositories. Wraps any software into a command-line interface with stateful sessions, undo/redo, and JSON output.
Apache-2.0 314 installs ★ 62,125 updated 2026-09-22
npx skills add HKUDS/CLI-Anything --skill cli-anything-hermes -a claude-codeWhat cli-anything-hermes does
Hermes analyzes the target software's architecture, designs a command hierarchy, and generates a Python harness in Click with a REPL mode as default, stateful operations, and rollback support. It wraps the real backend—either the target software's CLI or scripting interface—rather than reimplementing it.
Build mode creates a full project structure with setup.py, tests, and docs. Refine mode inventories an existing harness, runs gap analysis, and adds high-impact missing commands without removing old ones. Test and Validate modes check the namespace package layout, entry points, JSON output, and REPL path. Requires local access to the target software's source tree: clone from GitHub or work with a folder on disk.
What it helps with
- wrap a graphical application into a CLI for agents
- generate a Click app with stateful session and undo support
- add missing commands to an existing harness
- write tests for a CLI wrapper
- validate that a harness meets CLI-Anything standards
Example prompts for the agent
- Hermes, build a harness for GIMP, read
../cli-anything-plugin/HARNESS.md, and create the Click CLI structure with tests - Hermes, add frame and component commands to the Figma harness, run gap analysis against the API
- Hermes, write e2e and unit tests for the Blender harness, then run them via
cli-anything-blender
How to install cli-anything-hermes
1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-hermes -a claude-code2Manually: put the files in place
~/.claude/skills/hermes-skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/hermes-skill/
1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-hermes -a codex2Manually: put the files in place
.agents/skills/hermes-skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-hermes -a cursor2Manually: put the files in place
.cursor/skills/hermes-skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install HKUDS/CLI-Anything hermes-skill2Manually: put the files in place
.github/skills/hermes-skill/SKILL.md1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-hermes -a gemini-cli2Platform CLI
gemini skills install https://github.com/HKUDS/CLI-Anything --path hermes-skillManually: put the files in place
.devin/skills/hermes-skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-hermes -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cli-anything-hermes
How do I install cli-anything-hermes in Claude Code?
Run npx skills add HKUDS/CLI-Anything --skill cli-anything-hermes -a claude-code, then install hermes-skill: npx skills add HKUDS/CLI-Anything --skill hermes-skill -a claude-code. The skill profile opens in ~/.claude/skills/hermes-skill/SKILL.md.
What does cli-anything-hermes do?
It teaches a Hermes agent to build CLI wrappers over GUI applications. The agent analyzes the software's architecture, generates Click commands with state, undo/redo, and JSON output, and writes tests and documentation.
Do I need the source code of the target application?
Yes. The skill requires local access to the source tree—either cloned from GitHub or an existing folder on disk. It analyzes the architecture and wraps the real backend rather than reimplementing the software.
Source text
SKILL.md · Apache-2.0
---
name: cli-anything-hermes
description: Use when the user wants Hermes Agent to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository. Adapts the CLI-Anything methodology to Hermes without changing the generated Python harness format.
---
# CLI-Anything for Hermes Agent
Use this skill when the user wants Hermes Agent to act like the `CLI-Anything` builder.
Before implementation, use the full methodology source of truth when available:
1. If this skill is being used from inside the `CLI-Anything` repository, read `../cli-anything-plugin/HARNESS.md` first.
2. If that local file is unavailable, clone or download `cli-anything-plugin` from `https://github.com/HKUDS/CLI-Anything/tree/main/cli-anything-plugin`, then use `HARNESS.md` and the resources around it from that folder.
3. Only if both local and network retrieval fail, follow the condensed rules below.
## Inputs
Accept either:
- A local source path such as `./gimp` or `/path/to/software`
- A GitHub repository URL
Derive the software name from the local directory name after cloning if needed.
## Hermes Tool Bindings
Hermes agents build harnesses by combining these built-in tools:
| Tool | Role in Harness Workflow |
|------|--------------------------|
| `terminal` | Run shell commands, install packages, execute CLI tools, run tests |
| `execute_code` | Generate and write Python files (Click CLI, backend modules, tests) |
| `delegate_task` | Parallelize analysis or generation subtasks |
| `read_file` / `write_file` | Read and write harness source files |
| `patch` | Make targeted edits to generated code |
Consult the [Hermes Agent documentation](https://github.com/NousResearch/hermes-agent) for the exact tool invocation syntax.
## Modes
### Build
Use when the user wants a new harness.
Produce this structure:
```text
<software>/
└── agent-harness/
├── <SOFTWARE>.md
├── setup.py
└── cli_anything/
└── <software>/
├── README.md
├── __init__.py
├── __main__.py
├── <software>_cli.py
├── core/
├── utils/
└── tests/
```
Implement a stateful Click CLI with:
- one-shot subcommands
- REPL mode as the default when no subcommand is given
- `--json` machine-readable output
- session state with undo/redo where the target software supports it
### Refine
Use when the harness already exists.
First inventory current commands and tests, then do gap analysis against the target software. Prefer:
- high-impact missing features
- easy wrappers around existing backend APIs or CLIs
- additions that compose well with existing commands
Do not remove existing commands unless the user explicitly asks for a breaking change.
### Test
Plan tests before writing them. Keep both:
- `test_core.py` for unit coverage
- `test_full_e2e.py` for workflow and backend validation
When possible, test the installed command via subprocess using `cli-anything-<software>` rather than only module imports.
### Validate
Check that the harness:
- uses the `cli_anything.<software>` namespace package layout
- has an installable `setup.py` entry point
- supports JSON output
- has a REPL default path
- documents usage and tests
## Backend Rules
Prefer the real software backend over reimplementation. Wrap the actual executable or scripting interface in `utils/<software>_backend.py` when possible. Use synthetic reimplementation only when the project explicitly requires it or no viable native backend exists.
## Packaging Rules
- Use `find_namespace_packages(include=["cli_anything.*"])`
- Keep `cli_anything/` as a namespace package without a top-level `__init__.py`
- Expose `cli-anything-<software>` through `console_scripts`
## Workflow
1. Acquire the source tree locally (clone or use existing path).
2. Analyze architecture, data model, existing CLIs, and GUI-to-API mappings.
3. Design command groups and state model.
4. Implement the harness.
5. Write `TEST.md`, then tests, then run them.
6. Update README usage docs.
7. Verify local installation with `pip install -e .`
## Existing Harnesses (Reference)
For an up-to-date list of supported harnesses and their backend patterns, see [`registry.json`](../registry.json) at the repository root.
## Output Expectations
When reporting progress or final results, include:
- target software and source path
- files added or changed
- validation commands run
- open risks or backend limitations
© HKUDS · Apache-2.0 · HKUDS/CLI-Anything